Research map / Architectures and efficiency / RNNs and normalization
Neural-based classification rule learning for sequential data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use local model instead of global model (more expressive grammar) (ablation) | CR2N window 6, no pruning · Synthetic dataset 3b | balanced accuracy: 90.2 -> 97.1 | Helped |
| use local model instead of global model (ablation) | CR2N window 3, no pruning · Synthetic dataset 1b | balanced accuracy: 70.7 -> 100.0 | Helped |
| use local model instead of global model (ablation) | CR2N window 3, no pruning · Synthetic dataset 4 | penalty: 2.2 -> 28.6 | Hurt |
| use local model instead of global model (ablation) | CR2N window 6, no pruning · Peptides | accuracy: 91.2 -> 92.1 | No clear effect |
| use local model instead of global model (ablation) | CR2N window 6, no pruning · Peptides | penalty: 220.0 -> 3.9k | Hurt |
| increase convolution window from 3 to 6 (ablation) | CR2N global, no pruning · Peptides | accuracy: 88.9 -> 91.2 | Helped |
| increase convolution window from 3 to 6 (ablation) | CR2N local, no pruning · Synthetic dataset 3b | balanced accuracy: 89.8 -> 97.1 | Helped |
| increase convolution window from 3 to 6 (ablation) | CR2N global, no pruning · Synthetic dataset 2b | balanced accuracy: 90.5 -> 94.2 | Helped |
| add dynamic pruning from epoch 0 (ablation) | CR2N global window 6 · Peptides | accuracy: 91.2 -> 89.5 | Hurt |
| delay dynamic pruning until epoch 30 (ablation) | CR2N global window 6 · Peptides | accuracy: 91.2 -> 91.0 | No clear effect |
| add dynamic pruning from epoch 0 (ablation) | CR2N local window 6 · Synthetic dataset 4 | balanced accuracy: 99.1 -> 52.1 | Hurt |
| delay dynamic pruning until epoch 30 rather than epoch 0 (ablation) | CR2N local window 6 · Synthetic dataset 4 | balanced accuracy: 52.1 -> 79.3 | Helped |
Closest papers by meaning
- Finding Interpretable Class-Specific Patterns through Efficient Neural Search (AAAI 2024 · similarity 0.86)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.83)
- Differentiable Rule Induction from Raw Sequence Inputs (ICLR 2025 · similarity 0.83)
- Codebook Features: Sparse and Discrete Interpretability for Neural Networks (ICML 2024 · similarity 0.82)
- Neuro-Symbolic Temporal Point Processes (ICML 2024 · similarity 0.82)
- A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.